Zobrazeno 1 - 10
of 198
pro vyhledávání: '"Park, Jung Yeon"'
Data over non-Euclidean manifolds, often discretized as surface meshes, naturally arise in computer graphics and biological and physical systems. In particular, solutions to partial differential equations (PDEs) over manifolds depend critically on th
Externí odkaz:
http://arxiv.org/abs/2310.19589
Autor:
Zhao, Linfeng, Howell, Owen, Park, Jung Yeon, Zhu, Xupeng, Walters, Robin, Wong, Lawson L. S.
In robotic tasks, changes in reference frames typically do not influence the underlying physical properties of the system, which has been known as invariance of physical laws.These changes, which preserve distance, encompass isometric transformations
Externí odkaz:
http://arxiv.org/abs/2307.08226
Autor:
Wang, Dian, Zhu, Xupeng, Park, Jung Yeon, Jia, Mingxi, Su, Guanang, Platt, Robert, Walters, Robin
Although equivariant machine learning has proven effective at many tasks, success depends heavily on the assumption that the ground truth function is symmetric over the entire domain matching the symmetry in an equivariant neural network. A missing p
Externí odkaz:
http://arxiv.org/abs/2303.04745
Extensive work has demonstrated that equivariant neural networks can significantly improve sample efficiency and generalization by enforcing an inductive bias in the network architecture. These applications typically assume that the domain symmetry i
Externí odkaz:
http://arxiv.org/abs/2211.09231
Autor:
Park, Jung Yeon, Wong, Lawson L. S.
Behavior cloning of expert demonstrations can speed up learning optimal policies in a more sample-efficient way over reinforcement learning. However, the policy cannot extrapolate well to unseen states outside of the demonstration data, creating cova
Externí odkaz:
http://arxiv.org/abs/2210.09337
Incorporating symmetries can lead to highly data-efficient and generalizable models by defining equivalence classes of data samples related by transformations. However, characterizing how transformations act on input data is often difficult, limiting
Externí odkaz:
http://arxiv.org/abs/2204.11371
Autor:
Lee, Sungkyu, Yoo, Jounghyun, Bae, Gunhyu, Thangam, Ramar, Heo, Jeongyun, Park, Jung Yeon, Choi, Honghwan, Kim, Chowon, An, Jusung, Kim, Jungryun, Mun, Kwang Rok, Shin, Seungyong, Zhang, Kunyu, Zhao, Pengchao, Kim, Yuri, Kang, Nayeon, Han, Seong-Beom, Kim, Dahee, Yoon, Jiwon, Kang, Misun, Kim, Jihwan, Yang, Letao, Karamikamkar, Solmaz, Kim, Jinjoo, Zhu, Yangzhi, Najafabadi, Alireza Hassani, Song, Guosheng, Kim, Dong-Hwee, Lee, Ki-Bum, Oh, Soong Ju, Jung, Hyun-Do, Song, Hyun-Cheol, Jang, Woo Young, Bian, Liming, Chu, Zhiqin, Yoon, Juyoung, Kim, Jong Seung, Zhang, Yu Shrike, Kim, Yongju, Jang, Ho Seong, Kim, Sehoon, Kang, Heemin
Publikováno v:
In Bioactive Materials April 2024 34:164-180
Autor:
Smedemark-Margulies, Niklas, Park, Jung Yeon, Daniels, Max, Yu, Rose, van de Meent, Jan-Willem, Hand, Paul
Image recovery from compressive measurements requires a signal prior for the images being reconstructed. Recent work has explored the use of deep generative models with low latent dimension as signal priors for such problems. However, their recovery
Externí odkaz:
http://arxiv.org/abs/2102.11163
Efficient and interpretable spatial analysis is crucial in many fields such as geology, sports, and climate science. Tensor latent factor models can describe higher-order correlations for spatial data. However, they are computationally expensive to t
Externí odkaz:
http://arxiv.org/abs/2002.05578
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.